<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2139">
  <Title>Analysis of Japanese Compound Nouns using Collocational Information</Title>
  <Section position="7" start_page="867" end_page="868" type="evalu">
    <SectionTitle>
4 L
</SectionTitle>
    <Paragraph position="0"> We assumed that the thesaurus category of a tree bc represented by the category of its right branch subtree because Japanese is a head-final language. However, when a right subtrce is a word such as suffixes, this assumption does not always hold true. Since our ultimate aimis to analyze sc-mantle structures of compound nouns, then dealing with only the grammatical head is not enough.</Paragraph>
    <Paragraph position="1"> We should take semantic heads into consideration.</Paragraph>
    <Paragraph position="2"> In order to do so, however, we need knowledge to judge which subtrce represents tile semantic features of the tree. This knowledge may be extracted from corpora and machine readable dictionaries.</Paragraph>
    <Paragraph position="3"> A certain class of Japanese nouns (called Sahen meisi) may behave like verbs. Actually, we can make verbs frmn these nouns by adding a special verb &amp;quot;-suru.&amp;quot; These nouns have case frames just like ordinary verbs. With compound nouns including such nouns, wc coukl use case frames and sclectional restrictions to anMyzc structures. This process would be ahnost the same as analyzing ordinary sentences.</Paragraph>
  </Section>
class="xml-element"></Paper>